# A 71.2-μW Speech Recognition Accelerator with Recurrent Spiking Neural Network

arXiv: https://arxiv.org/abs/2503.21337 · HTML: https://mlsanity.com/paper/2503.21337/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Streaming automatic speech recognition with the transformer model](https://mlsanity.com/paper/2001.02674/) (2020)
- [The PyTorch-Kaldi Speech Recognition Toolkit](https://mlsanity.com/paper/1811.07453/) (2018)
- [Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition](https://mlsanity.com/paper/1911.08373/) (2019)
- [Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning](https://mlsanity.com/paper/2109.01905/) (2021)
- [Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2110.05267/) (2021)
- [Input-Aware Dynamic Timestep Spiking Neural Networks for Efficient In-Memory Computing](https://mlsanity.com/paper/2305.17346/) (2023)
- [Sparse Compressed Spiking Neural Network Accelerator for Object Detection](https://mlsanity.com/paper/2205.00778/) (2022)
- [Towards Energy-Efficient, Low-Latency and Accurate Spiking LSTMs](https://mlsanity.com/paper/2210.12613/) (2022)

## Built on by (most cited first, 1 of 1)

- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)

## Abstract (arXiv)

This paper introduces a 71.2-μW speech recognition accelerator designed for edge devices' real-time applications, emphasizing an ultra low power design. Achieved through algorithm and hardware co-optimizations, we propose a compact recurrent spiking neural network with two recurrent layers, one fully connected layer, and a low time step (1 or 2). The 2.79-MB model undergoes pruning and 4-bit fixed-point quantization, shrinking it by 96.42% to 0.1 MB. On the hardware front, we take advantage of textitmixed-level pruning, textitzero-skipping and textitmerged spike techniques, reducing complexity by 90.49% to 13.86 MMAC/S. The textitparallel time-step execution addresses inter-time-step data dependencies and enables weight buffer power savings through weight sharing. Capitalizing on the sparse spike activity, an input broadcasting scheme eliminates zero computations, further saving power. Implemented on the TSMC 28-nm process, the design operates in real time at 100 kHz, consuming 71.2 μW, surpassing state-of-the-art designs. At 500 MHz, it has 28.41 TOPS/W and 1903.11 GOPS/mm2 in energy and area efficiency, respectively.